tydymy/nucleotide-transformer-500m-1000g-finetuned-human-150bp-dna-classification

README.md

@@ -0,0 +1,68 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: InstaDeepAI/nucleotide-transformer-500m-1000g
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: nucleotide-transformer-500m-1000g-finetuned-human-150bp-dna-classification
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# nucleotide-transformer-500m-1000g-finetuned-human-150bp-dna-classification
+
+This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-500m-1000g](https://huggingface.co/InstaDeepAI/nucleotide-transformer-500m-1000g) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2793
+- Accuracy: 0.9411
+- F1: 0.9411
+- Precision: 0.9377
+- Recall: 0.9445
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.229         | 1.0   | 3125 | 0.2042          | 0.9187   | 0.9203 | 0.8977    | 0.9440 |
+| 0.2019        | 2.0   | 6250 | 0.2176          | 0.9360   | 0.9340 | 0.9590    | 0.9102 |
+| 0.0008        | 3.0   | 9375 | 0.2958          | 0.9397   | 0.9395 | 0.9371    | 0.9420 |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "InstaDeepAI/nucleotide-transformer-500m-1000g",
+  "architectures": [
+    "EsmForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "is_folding_model": false,
+  "layer_norm_eps": 1e-12,
+  "mask_token_id": 2,
+  "max_position_embeddings": 1002,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": false,
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": false,
+  "vocab_list": null,
+  "vocab_size": 4105
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:313d1f6b0b265cfc4ebc9b76c83a5400dc4bbf9829e663ebe87582f772d56507
+size 1921809396

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c19d5f70a9e97e91617c13ef7a386737c53d30309848f563258294b751e851
+size 4600